Optimize
Spend the fewest tokens for the best result
A complete, tool-by-tool playbook for token and credit optimization — from prompt caching and model routing to the viral Caveman method. Plan first, pick the smallest sufficient model, reuse outputs, and batch.
16 techniques
Techniques Catalog
Every high-leverage way to cut tokens — caching, routing, compression, RAG, output control and more.
Open7 tools
Tool-Specific Guides
Playbooks for Claude, Lovable, ChatGPT/OpenAI, Gemini, Cursor, Copilot and media tools.
OpenDeep dive
Caveman Compression
The telegram-style prompt method: drop filler, keep meaning, save 14–45% of tokens.
Open8 templates
Prompt Templates
Copy-paste scaffolds for caching, routing, output control, compaction and project memory.
Open The four moves that win every time
Plan first
Architect & draft in a free chat before spending paid tokens/credits.
Smallest model
Route by difficulty; escalate only on low confidence.
Reuse outputs
Cache prefixes, cache answers, reuse renders & clips.
Batch
Queue non-urgent work for ~50% off.
Pricing, discounts, and TTLs change frequently. Always confirm current numbers in the provider's own docs before relying on them for budgeting. Last reviewed June 2026.